Narrative flow profile
PR review agent
Stacked semantic review for merge safety.
Abstract pattern
Stacked semantic review
Shows how deterministic checks and semantic review can work together before a change reaches the merge gate.
- Manual Instrumented boundary; human performs the governed effect.
- HITL Automation proposes or prepares the effect and a human authorizes it before execution.
- HOTL The effect executes with asynchronous human oversight.
- Autonomous The effect executes under declared evaluator and demotion policy.
Narrative task profile
PR review agent
Shows how deterministic checks and semantic review can work together before a change reaches the merge gate.
- Boundary
- Input is the PR diff plus context like the linked issue and test results. Output is a structured review verdict of approve, request-changes, or escalate with rationale.
- Evidence log
- Diff, test results, lint results, judge verdict, human decision when gated, and whether a later merge needed a revert or caused an incident.
- Evaluator
-
- Property
- merge_readiness
- Target
- Output
- Technique
- Deterministic tests and lint run first, then an LLM judge handles the semantic call the deterministic layer cannot make.
- Evaluation basis
- rubric: senior_reviewer_rubric_checked_against_test_and_lint_reference_results
- Epistemic status
- proxy
- Version
- 1
- Authority
- blocking
- Placement notes
-
- hitl
- blocking, agent verdict is held at the merge gate until a human reviewer clears it
- hotl
- sampling, only flagged or high-risk PRs re-enter blocking review; low-risk PRs proceed after sampled monitoring
- Promotion rule
- Judge agreement with senior reviewers stays above threshold over a window and deterministic escapes stay near zero, allowing the flow to shift from blocking review to sampled monitoring.
- Demotion
-
- Rule
- A merged auto-approved PR causes a revert or incident, or judge-vs-human agreement drifts down.
- Fallback
- Human review stays on the merge path for substantive changes.
Teaching point
What this flow proves
Cheap deterministic checks can stack under an expensive semantic judge, and the artifact boundary itself is the thing being reviewed.
Teaching context
Why this flow is governed this way
- Worker context
- LLM + tools
- Without PAA
- Merges rely on whoever happens to review the PR; semantic quality is informal and inconsistent; the merge gate has no systematic bar and no audit trail when something ships that should not have.
- Never full-auto
- Substantive semantic judgment, an LLM judge can own the first-pass review but not the final merge gate without ongoing human validation.
This page is linked from the canonical card set on the flows index.